Hidden Monitoring Based on Keystroke Dynamics in Online Examination System

The COVID-19 pandemic has accelerated the development of distance learning technologies, where online tests and exams play an important role. In testing, detection various types academic fraud, including cases examinee is falsely represented by another person, particular importance. Continuous biometric (behavioral) authentication can be a solution to counter unauthorized access. This paper proposes technology based on keystroke dynamics hidden monitoring. An application for collecting updating profiles domain users their continuous developed. efficiency reducing dimension feature space frequency alphabetic letters demonstrated. Results popular performance metrics (FAR, FRR, ERR, ROC, DET) are significantly improved already when evaluating only metric distances. For instance, ERR reduced from 10.1% 0.79%, which comparable estimates provided kNN method its optimal parameters.